# Low-Resource End-to-end Sanskrit TTS using Tacotron2, WaveGlow and Transfer Learning

arXiv: https://arxiv.org/abs/2212.03558 · HTML: https://mlsanity.com/paper/2212.03558/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 7 Dec 2022.

## Builds on (most cited first, 8 of 8)

- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [Tacotron: Towards End-to-End Speech Synthesis](https://mlsanity.com/paper/1703.10135/) (2017)
- [WaveGlow: A Flow-based Generative Network for Speech Synthesis](https://mlsanity.com/paper/1811.00002/) (2018)
- [Transfer Learning from Speaker Verification to Multispeaker Text-To-Speech Synthesis](https://mlsanity.com/paper/1806.04558/) (2018)
- [Deep Voice: Real-time Neural Text-to-Speech](https://mlsanity.com/paper/1702.07825/) (2017)
- [Exploring Transfer Learning for Low Resource Emotional TTS](https://mlsanity.com/paper/1901.04276/) (2019)
- [Towards Transfer Learning for End-to-End Speech Synthesis from Deep Pre-Trained Language Models](https://mlsanity.com/paper/1906.07307/) (2019)
- [Towards Robust Neural Vocoding for Speech Generation: A Survey](https://mlsanity.com/paper/1912.02461/) (2019)

## Built on by (most cited first, 2 of 2)

- [VAKTA-SETU: A Speech-to-Speech Machine Translation Service in Select Indic Languages](https://mlsanity.com/paper/2305.12518/) (2023)
- [Text to Speech System for Meitei Mayek Script](https://mlsanity.com/paper/2508.06870/) (2025)

## Abstract (arXiv)

End-to-end text-to-speech (TTS) systems have been developed for European languages like English and Spanish with state-of-the-art speech quality, prosody, and naturalness. However, development of end-to-end TTS for Indian languages is lagging behind in terms of quality. The challenges involved in such a task are: 1) scarcity of quality training data; 2) low efficiency during training and inference; 3) slow convergence in the case of large vocabulary size. In our work reported in this paper, we have investigated the use of fine-tuning the English-pretrained Tacotron2 model with limited Sanskrit data to synthesize natural sounding speech in Sanskrit in low resource settings. Our experiments show encouraging results, achieving an overall MOS of 3.38 from 37 evaluators with good Sanskrit spoken knowledge. This is really a very good result, considering the fact that the speech data we have used is of duration 2.5 hours only.